iCFP: Tolerating All-Level Cache Misses in In-Order Processors
| Autor: | Andrew D. Hilton, Santosh Nagarakatte, Amir Roth |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Hardware_MEMORYSTRUCTURES
Computer science Pipeline (computing) Register file Cache miss Parallel computing computer.software_genre Hardware and Architecture Order (exchange) Multithreading Operating system State (computer science) Cache Hardware_CONTROLSTRUCTURESANDMICROPROGRAMMING Electrical and Electronic Engineering computer Data cache Software |
| Zdroj: | HPCA |
| ISSN: | 0272-1732 |
| DOI: | 10.1109/mm.2010.20 |
| Popis: | In-order continual flow pipeline (iCFP) is an in-order pipeline that allows execution to flow around data cache misses. When a cache miss occurs, iCFP executes and speculatively retires miss-independent instructions. It saves miss-dependent instructions in a slice buffer. When the miss returns, iCFP reexecutes the contents of the slice buffer and merges the results into working state. iCFP exploits existing support for multithreading and several novel components. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|